Abstract
Efficient drug discovery relies on drug repurposing, an important and open research field. This work presents a novel factorization method and a practical comparison of different approaches for drug repurposing. First, we propose a novel tensor-matrix-tensor (TMT) formulation as a new data array method with a gradient-based factorization procedure. Additionally, this paper examines and contrasts four computational drug repurposing approaches—factorization-based methods, machine learning methods, deep learning methods, and graph neural networks—to fulfill the second purpose. We test the strategies on two datasets and assess each approach’s performance, drawbacks, problems, and benefits based on results. The results demonstrate that deep learning techniques work better than other strategies and that their results might be more reliable. Ultimately, graph neural methods need to be in an inductive manner to have a reliable prediction.
Similar content being viewed by others
Data availability
The data and code are freely available at github.com/BioinformaticsIASBS/Tensor.
Materials availability
Not applicable.
References
Denny JC, Collins FS (2021) Precision medicine in 2030—seven ways to transform healthcare. Cell 184(6):1415–1419. https://doi.org/10.1016/j.cell.2021.01.015
Taylor K, Das S, Pearson M et al (2019) Systematic drug repurposing to enable precision medicine: a case study in breast cancer. Digital Medicine 5(4):180–186. https://doi.org/10.1016/j.cell.2021.01.015
Bagherian M, Sabeti E, Wang K et al (2021) Machine learning approaches and databases for prediction of drug–target interaction: a survey paper. Brief Bioinform 22(1):247–269. https://doi.org/10.1093/bib/bbz157
To KK, Cho WC (2022) Drug repurposing for cancer therapy in the era of precision medicine. Curr Mol Pharmacol 15:895–903. https://doi.org/10.2174/1874467215666220214104530
Lo YC (2016) Chemical dissection of the cell cycle for anticancer drug discovery and target identification. PhD thesis, UCLA
Zhang R, Wang Z, Wang X et al (2023) Mhtan-dti: metapath-based hierarchical transformer and attention network for drug–target interaction prediction. Brief Bioinf 24(2):bbad079. https://doi.org/10.1093/bib/bbad079
Chen H, Li J (2019) Modeling relational drug-target-disease interactions via tensor factorization with multiple web sources. In: The World Wide Web conference, pp 218–227. https://doi.org/10.1145/3308558.3313476
von Davier AA, Wong PC, Polyak S, et al (2019) The argument for a “data cube” for large-scale psychometric data. In: Frontiers in Education, Frontiers Media SA, p 71. https://doi.org/10.3389/feduc.2019.00071
Patil VA, Jayaswal DJ (2020) Context relevancy assessment in tensor factorization-based recommender systems. In: 2020 3rd international conference on communication system, computing and it applications (CSCITA), IEEE, pp 141–145. https://doi.org/10.1109/CSCITA47329.2020.9137778
Yao J, Hurle MR, Nelson MR et al (2019) Predicting clinically promising therapeutic hypotheses using tensor factorization. BMC Bioinform 20(1):1–12. https://doi.org/10.1186/s12859-019-2664-1
Ebied AMA (2019) Higher-order tensor decompositions for muscle synergy analysis. PhD thesis, The University of Edinburgh
Turchetti C (2023) Decomposition of linear tensor transformations. https://doi.org/10.48550/arXiv.2309.07819
Luo Y, Zhao X, Zhou J et al (2017) A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nat Commun 8(1):1–13. https://doi.org/10.1038/s41467-017-00680-8
Yamanishi Y, Araki M, Gutteridge A et al (2008) Prediction of drug–target interaction networks from the integration of chemical and genomic spaces. Bioinformatics 24(13):i232–i240. https://doi.org/10.1093/bioinformatics/btn162
Wang YX, Zhang YJ (2012) Nonnegative matrix factorization: a comprehensive review. IEEE Trans Knowl Data Eng 25(6):1336–1353. https://doi.org/10.1109/TKDE.2012.51
Cichocki A, Zdunek R, Si A (2007) Nonnegative matrix and tensor factorization [lecture notes]. IEEE Signal Process Mag 25(1):142–145. https://doi.org/10.1109/MSP.2008.4408452
Acar E, Dunlavy DM, Kolda TG (2011) A scalable optimization approach for fitting canonical tensor decompositions. J Chemom 25(2):67–86. https://doi.org/10.1002/cem.1335
Cichocki A, Mandic D, De Lathauwer L et al (2015) Tensor decompositions for signal processing applications: from two-way to multiway component analysis. IEEE Signal Process Mag 32(2):145–163. https://doi.org/10.1109/MSP.2013.2297439
Papalexakis EE, Faloutsos C, Sidiropoulos ND (2016) Tensors for data mining and data fusion: models, applications, and scalable algorithms. ACM Trans Intell Syst Technol 8(2):1–44. https://doi.org/10.1145/2915921
Ezzat A, Wu M, Li XL et al (2019) Computational prediction of drug—target interactions using chemogenomic approaches: an empirical survey. Brief Bioinform 20(4):1337–1357. https://doi.org/10.1093/bib/bby002
Chen R, Liu X, Jin S et al (2018) Machine learning for drug-target interaction prediction. Molecules 23(9):2208. https://doi.org/10.3390/molecules23092208
Kim Y, Bismeijer T, Zwart W et al (2019) Genomic data integration by wonparafac identifies interpretable factors for predicting drug-sensitivity in vivo. Nat Commun 10(1):5034. https://doi.org/10.1038/s41467-019-13027-2
Martins RS, da Costa Gomes MF, Caffarena ER (2022) Combining network-based and matrix factorization to predict novel drug-target interactions: a case study using the brazilian natural chemical database. Curr Bioinform 17(9):793–803. https://doi.org/10.2174/1574893617666220820105258
Tang X, Cai L, Meng Y et al (2021) Indicator regularized non-negative matrix factorization method-based drug repurposing for covid-19. Front Immunol. https://doi.org/10.3389/fimmu.2020.603615
Guvenc Paltun B, Mamitsuka H, Kaski S (2021) Improving drug response prediction by integrating multiple data sources: matrix factorization, kernel and network-based approaches. Brief Bioinform 22(1):346–359. https://doi.org/10.1093/bib/bbz153
Kaya O, Ucar B (2018) Parallel candecomp/parafac decomposition of sparse tensors using dimension trees. SIAM J Sci Comput 40(1):C99–C130. https://doi.org/10.1137/16M1102744
Uschmajew A, Vandereycken B (2013) The geometry of algorithms using hierarchical tensors. Linear Algebra App 439(1):133–166. https://doi.org/10.1016/j.laa.2013.03.016
Acar E, Kolda TG, Dunlavy DM (2011) All-at-once optimization for coupled matrix and tensor factorizations. https://doi.org/10.48550/arXiv.1105.3422
Acar E, Rasmussen MA, Savorani F et al (2013) Understanding data fusion within the framework of coupled matrix and tensor factorizations. Chemom Intell Lab Syst 129:53–63. https://doi.org/10.1016/j.chemolab.2013.06.006
Balasubramaniam T, Nayak R, Yuen C (2019) Nonnegative coupled matrix tensor factorization for smart city spatiotemporal pattern mining. In: Machine learning, optimization, and data science: 4th international conference, LOD 2018, Volterra, Italy, September 13–16, 2018, Revised Selected Papers 4, Springer, pp. 520–532. https://doi.org/10.1007/978-3-030-13709-0 44
Thirunavukarasu B, Nayak R, Yuen C (2020) Column-wise element selection for computationally efficient nonnegative coupled matrix tensor factorization. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2020.2967045
Acar E, Bro R, Smilde AK (2015) Data fusion in metabolomics using coupled matrix and tensor factorizations. Proc IEEE 103(9):1602–1620. https://doi.org/10.1109/JPROC.2015.2438719
Mosayebi R, Hossein-Zadeh GA (2020) Correlated coupled matrix tensor factorization method for simultaneous eeg-fmri data fusion. Biomed Signal Process Control 62:102071. https://doi.org/10.1016/j.bspc.2020.102071
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. Int Conf Learn Representations. Doi: https://doi.org/10.48550/arXiv.1412.6980
Qi L, Hu S, Zhang X, et al (2019) Tensor norm, cubic power and gelfand limit. https://doi.org/10.48550/arXiv.1909.10942
Liu S, Trenkler G et al (2008) Hadamard, Khatri-Rao, Kronecker and other matrix products. Int J Inf Syst Sciences 4(1):160–177
Han J, Kamber M, Pei J (2012) Data mining concepts and techniques, 3rd edn. Morgan Kaufmann
Hashemi SM, Zabihian A, Hooshmand M et al (2023) Draw: prediction of covid19 antivirals by deep learning—an objection on using matrix factorization. BMC Bioinform 24(1):52. https://doi.org/10.1186/s12859-023-05181-8
Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27. https://doi.org/10.1109/TIT.1967.1053964
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785–794. https://doi.org/10.1145/2939672.2939785
Shi H, Liu S, Chen J et al (2019) Predicting drug-target interactions using lasso with random forest based on evolutionary information and chemical structure. Genomics 111(6):1839–1852. https://doi.org/10.1016/j.ygeno.2018.12.007
Keum J, Nam H (2017) SELF-BLM: prediction of drug-target interactions via self-training SVM. PLoS ONE 12(2):1–16. https://doi.org/10.1371/journal.pone.0171839
Jarada TN, Rokne JG, Alhajj R (2020) A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions. J Cheminf 12(1):1–23. https://doi.org/10.1186/s13321-020-00450-7
Dinesh P, Kalyanasundaram P (2022) Medical image prediction for diagnosis of breast cancer disease comparing the machine learning algorithms: Svm, knn, logistic regression, random forest, and decision tree to measure accuracy. ECS Trans 107(1):12681. https://doi.org/10.1149/10701.12681ecst
Pranckevicius T, Marcinkevicius V (2017) Comparison of Naive Bayes, random forest, decision tree, support vector machines, and logistic regression classifiers for text reviews classification. Baltic J Modern Comput 5(2):221. https://doi.org/10.22364/BJMC.2017.5.2.05
Playe B, Stoven V (2020) Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity. J Cheminf 12(1):11. https://doi.org/10.1186/s13321-020-0413-0
Beck BR, Shin B, Choi Y et al (2020) Predicting commercially available antiviral drugs that may act on the novel coronavirus (sars-cov-2) through a drug-target interaction deep learning model. Comput Struct Biotechnol J 18:784–790. https://doi.org/10.1016/j.csbj.2020.03.025
Senior AW, Evans R, Jumper J et al (2020) Improved protein structure prediction using potentials from deep learning. Nature 577(7792):706–710. https://doi.org/10.1038/s41586-019-1923-7
Shin B, Park S, Kang K, et al (2019) Self-attention based molecule representation for predicting drug-target interaction. In: Machine learning for healthcare conference. PMLR, pp. 230–248
Zeng X, Song X, Ma T et al (2020) Repurpose open data to discover therapeutics for covid-19 using deep learning. J Proteome Res 19(11):4624–4636. https://doi.org/10.1021/acs.jproteome.0c00316
Huang K, Xiao C, Glass LM et al (2021) MolTrans: molecular interaction transformer for drug-target interaction prediction. Bioinformatics 37(6):830–836. https://doi.org/10.1093/bioinformatics/btaa880
Kalakoti Y, Yadav S, Sundar D (2022) TransDTI: transformer-based language models for estimating DTIs and building a drug recommendation workflow. ACS Omega 7(3):2706–2717. https://doi.org/10.1021/acsomega.1c05203
Bordes A, Usunier N, Garcia-Duran A, et al (2013) Translating embeddings for modeling multi-relational data. In: Advances in neural information processing systems
Zabihian A, Sayyad FZ, Hashemi SM et al (2023) Dedti versus iedti: efficient and predictive models of drug-target interactions. Sci Rep 13(1):9238. https://doi.org/10.1038/s41598-023-36438-0
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. https://doi.org/10.48550/arXiv.1609.02907
Hamilton WL (2020) Graph representation learning. Morgan & Claypool Publishers, California
Yang Y, Su X, Zhao B et al (2023) Fuzzy-based deep attributed graph clustering. IEEE Trans Fuzzy Syst. https://doi.org/10.1109/TFUZZ.2023.3338565
Wang L, Li ZW, You ZH et al (2023) Gslcda: an unsupervised deep graph structure learning method for predicting circrna-disease association. IEEE J Biomed Health Inform. https://doi.org/10.1109/JBHI.2023.3344714
Wan F, Hong L, Xiao A et al (2019) Neodti: neural integration of neighbor information from a heterogeneous network for discovering new drug–target interactions. Bioinformatics 35(1):104–111. https://doi.org/10.1093/bioinformatics/bty543
Zhao T, Hu Y, Valsdottir LR et al (2021) Identifying drug–target interactions based on graph convolutional network and deep neural network. Brief Bioinform 22(2):2141–2150. https://doi.org/10.1093/bib/bbaa044
Peng J, Wang Y, Guan J et al (2021) An end-to-end heterogeneous graph representation learning-based framework for drug–target interaction prediction. Brief Bioinform 22(5):bbaa430. https://doi.org/10.1093/bib/bbaa430
Li J, Wang J, Lv H et al (2022) IMCHGAN: inductive matrix completion with heterogeneous graph attention networks for drug-target interactions prediction. IEEE/ACM Trans Comput Biol Bioinform 19(2):655–665. https://doi.org/10.1109/TCBB.2021.3088614
Rossi A, Tiezzi M, Dimitri GM, et al (2018) Inductive–transductive learning with graph neural networks. In: Artificial neural networks in pattern recognition: 8th IAPR TC3 workshop, ANNPR 2018, Siena, Italy, September 19–21, 2018, Proceedings 8, Springer, pp 201–212. https://doi.org/10.1109/TPAMI.2021.3054304
Fu X, Zhang J, Meng Z et al (2020) Magnn: metapath aggregated graph neural network for heterogeneous graph embedding. Proc Web Conf 2020:2331–2341. https://doi.org/10.1145/3366423.3380297
Tanha RS, Sadighian M, Zabihian A, et al (2023) Mad-ti: meta-path aggregatedgraph attention network for drug target interaction prediction. In: 2023 31st international conference on electrical engineering (ICEE), IEEE, pp 619–624. https://doi.org/10.1109/ICEE59167.2023.10334728
Bottou L, Lin CJ et al (2007) Support vector machine solvers. Large Scale Kernel Machines 3(1):301–320. https://doi.org/10.7551/mitpress/7496.003.0003
Velickovic P, Cucurull G, Casanova A, et al (2018) Graph attention networks. International Conference on Learning Representations. https://openreview.net/forum?id=rJXMpikCZ
Chicco D, Jurman G (2020) The advantages of the matthews correlation coefficient (MCC) over f1 score and accuracy in binary classification evaluation. BMC Genomics 21(1):6. https://doi.org/10.1186/s12864-019-6413-7
Fan J, Upadhye S, Worster A (2006) Understanding receiver operating characteristic (ROC) curves. Can J Emergency Med 8(1):19–20. https://doi.org/10.4097/kja.21209
Teru KK, Denis EG, Hamilton WL (2020) Inductive relation prediction by subgraph reasoning. In: Proceedings of the 37th international conference on machine learning. JMLR.org, ICML’20
Soh J, Park S, Lee H (2022) Hidti: integration of heterogeneous information to predict drug-target interactions. Sci Rep 12(1):1–12. https://doi.org/10.1038/s41598-022-07608-3
Zhao BW, Su XR, Hu PW et al (2023) igrldti: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network. Bioinformatics 39(8):btad451. https://doi.org/10.1093/bioinformatics/btad451
Jin J, Wang Y, Du K, et al (2022) Inductive relation prediction using analogy subgraph embeddings. In: International conference on learning representations. https://openreview.net/forum?id=PTRo58zPt3P
Lee J, Chung C, Whang JJ (2023) Ingram: Inductive knowledge graph embedding via relation graphs. CoRR abs/2305.19987. https://doi.org/10.48550/ARXIV.2305.19987
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. https://doi.org/10.1007/BF00994018
Ho TK (1995) Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition. IEEE, pp 278–282. https://doi.org/10.1109/ICDAR.1995.598994
Acknowledgements
The authors would like to thank Reza Shami Tanha for providing the results of MAD-TI.
Author information
Authors and Affiliations
Contributions
MH and AZ conceptualized the idea. JA implemented the methods. MH, AZ, and JA conceptualized the idea and wrote the manuscript. MH supervised and administered the project. SG proofread the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interest
The authors declare that they have no competing interests.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zabihian, A., Asghari, J., Hooshmand, M. et al. A comparative analysis of computational drug repurposing approaches: proposing a novel tensor-matrix-tensor factorization method. Mol Divers (2024). https://doi.org/10.1007/s11030-024-10851-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11030-024-10851-7